# This will help in making the Python code more structured automatically (good coding practice)
%load_ext nb_black

# Libraries to help with reading and manipulating data
import pandas as pd
import numpy as np

# Libaries to help with data visualization
import matplotlib.pyplot as plt
import seaborn as sns

# To tune model, get different metric scores, and split data
from sklearn.metrics import (
    f1_score,
    accuracy_score,
    recall_score,
    precision_score,
    confusion_matrix,
    roc_auc_score,
    plot_confusion_matrix,
)
from sklearn import metrics

from sklearn.model_selection import train_test_split, StratifiedKFold, cross_val_score

# To be used for data scaling and one hot encoding
from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder

# To impute missing values
from sklearn.impute import SimpleImputer

# To oversample and undersample data
from imblearn.over_sampling import SMOTE
from imblearn.under_sampling import RandomUnderSampler

# To do hyperparameter tuning
from sklearn.model_selection import RandomizedSearchCV

# To be used for creating pipelines and personalizing them
from sklearn.pipeline import Pipeline
from sklearn.compose import ColumnTransformer

# To define maximum number of columns to be displayed in a dataframe
pd.set_option("display.max_columns", None)
pd.set_option("display.max_rows", None)

# To supress scientific notations for a dataframe
pd.set_option("display.float_format", lambda x: "%.3f" % x)

# To help with model building
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import (
    AdaBoostClassifier,
    GradientBoostingClassifier,
    RandomForestClassifier,
    BaggingClassifier,
)
from xgboost import XGBClassifier

# To suppress scientific notations
pd.set_option("display.float_format", lambda x: "%.3f" % x)

# To suppress warnings
import warnings

warnings.filterwarnings("ignore")

from pandas import ExcelWriter
from pandas import ExcelFile

df = pd.ExcelFile("covid19_dataset.xlsx")

df = pd.read_excel(r"/Users/himadrisamanta/Downloads/covid19_dataset.xlsx")
df.to_csv(
    r"/Users/himadrisamanta/Downloads/covid19_dataset.csv", index=None, header=True
)

data1 = pd.read_csv("covid19_dataset.csv")

pd.set_option("display.max_columns", None)

data1.sample(5, random_state=1)

print(f"There are {data1.shape[0]} rows and {data1.shape[1]} columns in  data.")

data1.info()

data = data1.copy()

data.duplicated().sum()

data.isnull().sum().T

data.describe().T

data.head()

data.drop(["Patient ID"], axis=1, inplace=True)

data.columns = [c.replace("#", "") for c in data.columns]
data.columns = [c.replace("-", "") for c in data.columns]
data.columns = [c.replace("=", "") for c in data.columns]
data.columns = [c.replace("(", "") for c in data.columns]
data.columns = [c.replace(")", "") for c in data.columns]
data.columns = [c.replace("<", "") for c in data.columns]
data.columns = [c.replace(",", "") for c in data.columns]
data.columns = [c.replace(" ", "") for c in data.columns]
data.columns = [c.replace("/", "") for c in data.columns]

data.sample(5, random_state=1)

cat_col = list(data.select_dtypes("object").columns)

# Printing number of count of each unique value in each column
for column in cat_col:
    print(data[column].value_counts())
    print("-" * 50)

cat_col

data["SARSCov2examresult"] = data["SARSCov2examresult"].apply(
    lambda x: 1 if x == "positive" else 0
)
data["RespiratorySyncytialVirus"] = data["RespiratorySyncytialVirus"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["InfluenzaA"] = data["InfluenzaA"].apply(lambda x: 1 if x == "detected" else 0)
data["InfluenzaB"] = data["InfluenzaB"].apply(lambda x: 1 if x == "detected" else 0)
data["Parainfluenza1"] = data["Parainfluenza1"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["CoronavirusNL63"] = data["CoronavirusNL63"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["RhinovirusEnterovirus"] = data["RhinovirusEnterovirus"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["CoronavirusHKU1"] = data["CoronavirusHKU1"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["Parainfluenza3"] = data["Parainfluenza3"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["Chlamydophilapneumoniae"] = data["Chlamydophilapneumoniae"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["Adenovirus"] = data["Adenovirus"].apply(lambda x: 1 if x == "detected" else 0)
data["Parainfluenza4"] = data["Parainfluenza4"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["Coronavirus229E"] = data["Coronavirus229E"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["CoronavirusOC43"] = data["CoronavirusOC43"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["InfAH1N12009"] = data["InfAH1N12009"].apply(lambda x: 1 if x == "detected" else 0)
data["Bordetellapertussis"] = data["Bordetellapertussis"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["Metapneumovirus"] = data["Metapneumovirus"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["Parainfluenza2"] = data["Parainfluenza2"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["InfluenzaBrapidtest"] = data["InfluenzaBrapidtest"].apply(
    lambda x: 1 if x == "detected" else 0
)
data["StreptoA"] = data["StreptoA"].apply(lambda x: 1 if x == "detected" else 0)
data5["InfluenzaBrapidtest"] = data5["InfluenzaBrapidtest"].apply(
    lambda x: 1 if x == "positive" else 0
)
data["InfluenzaArapidtest"] = data["InfluenzaArapidtest"].apply(
    lambda x: 1 if x == "positive" else 0
)

data.sample(5, random_state=1)

# function to create labeled barplots


def labeled_barplot(df, feature, perc=False, n=None):
    """
    Barplot with percentage at the top

    data: dataframe
    feature: dataframe column
    perc: whether to display percentages instead of count (default is False)
    n: displays the top n category levels (default is None, i.e., display all levels)
    """

    total = len(df[feature])  # length of the column
    count = df[feature].nunique()
    if n is None:
        plt.figure(figsize=(count + 1, 5))
    else:
        plt.figure(figsize=(n + 1, 5))

    plt.xticks(rotation=90, fontsize=15)
    ax = sns.countplot(
        data=df,
        x=feature,
        palette="Paired",
        order=df[feature].value_counts().index[:n].sort_values(),
    )

    for p in ax.patches:
        if perc == True:
            label = "{:.1f}%".format(
                100 * p.get_height() / total
            )  # percentage of each class of the category
        else:
            label = p.get_height()  # count of each level of the category

        x = p.get_x() + p.get_width() / 2  # width of the plot
        y = p.get_height()  # height of the plot

        ax.annotate(
            label,
            (x, y),
            ha="center",
            va="center",
            size=12,
            xytext=(0, 5),
            textcoords="offset points",
        )  # annotate the percentage

    plt.show()  # show the plot

# function to plot a boxplot and a histogram along the same scale.


def histogram_boxplot(data, feature, figsize=(12, 7), kde=False, bins=None):
    """
    Boxplot and histogram combined

    data: dataframe
    feature: dataframe column
    figsize: size of figure (default (12,7))
    kde: whether to the show density curve (default False)
    bins: number of bins for histogram (default None)
    """
    f2, (ax_box2, ax_hist2) = plt.subplots(
        nrows=2,  # Number of rows of the subplot grid= 2
        sharex=True,  # x-axis will be shared among all subplots
        gridspec_kw={"height_ratios": (0.25, 0.75)},
        figsize=figsize,
    )  # creating the 2 subplots
    sns.boxplot(
        data=data, x=feature, ax=ax_box2, showmeans=True, color="violet"
    )  # boxplot will be created and a star will indicate the mean value of the column
    sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2, bins=bins, palette="winter"
    ) if bins else sns.histplot(
        data=data, x=feature, kde=kde, ax=ax_hist2
    )  # For histogram
    ax_hist2.axvline(
        data[feature].mean(), color="green", linestyle="--"
    )  # Add mean to the histogram
    ax_hist2.axvline(
        data[feature].median(), color="black", linestyle="-"
    )  # Add median to the histogram

result = data.select_dtypes(include="number")
result.head()

for feature in result.columns:
    histogram_boxplot(
        result, feature, figsize=(12, 7), kde=False, bins=None
    )  ## Please change the dataframe name as you define while reading the data

result1 = data.select_dtypes(include="object")
result1.head()

for feature in result1.columns:
    labeled_barplot(
        result1, feature, perc=True
    )  ## Please change the dataframe name as you define while reading the data

# correlation check
plt.figure(figsize=(41, 37))
sns.heatmap(data.corr(), annot=True, vmin=-1, vmax=1, fmt=".1f", cmap="Spectral")
plt.show()

plt.figure(figsize=(7, 6))
sns.barplot(
    data=data, x="SARSCov2examresult", y="VitaminB12", ci=False
)  ## Complete the code to choose the right variables
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(7, 6))
sns.barplot(
    data=data, x="SARSCov2examresult", y="Hematocrit", ci=False
)  ## Complete the code to choose the right variables
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(7, 6))
sns.barplot(data=data, x="SARSCov2examresult", y="Hemoglobin", ci=False)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(7, 6))
sns.barplot(data=data, x="SARSCov2examresult", y="Platelets", ci=False)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(
    data=data, x="SARSCov2examresult", y="TotalCO2arterialbloodgasanalysis", ci=False
)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(data=data, x="SARSCov2examresult", y="RedbloodCells", ci=False)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(data=data, x="SARSCov2examresult", y="Lymphocytes", ci=False)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(
    data=data, x="SARSCov2examresult", y="Patientaddmitedtoregularward1yes0no", ci=False
)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(data=data, x="SARSCov2examresult", y="Leukocytes", ci=False)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(7, 5))
sns.countplot(x="RespiratorySyncytialVirus", hue="SARSCov2examresult", data=data)
plt.xticks(rotation=60)
plt.legend(loc=1)
plt.show()

plt.figure(figsize=(7, 5))
sns.countplot(x="RhinovirusEnterovirus", hue="SARSCov2examresult", data=data)
plt.xticks(rotation=60)
plt.legend(loc=1)
plt.show()

plt.figure(figsize=(7, 5))
sns.countplot(x="InfluenzaB", hue="SARSCov2examresult", data=data)
plt.xticks(rotation=60)
plt.legend(loc=1)
plt.show()

plt.figure(figsize=(7, 5))
sns.countplot(x="UrinepH", hue="SARSCov2examresult", data=data)
plt.xticks(rotation=60)
plt.legend(loc=1)
plt.show()

plt.figure(figsize=(7, 5))
sns.countplot(x="Patientagequantile", hue="SARSCov2examresult", data=data)
plt.xticks(rotation=60)
plt.legend(loc=1)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(
    data=data, y="Leukocytes", x="Patientaddmitedtoregularward1yes0no", ci=False
)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(
    data=data, y="Leukocytes", x="Patientaddmitedtosemiintensiveunit1yes0no", ci=False
)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(
    data=data, y="Leukocytes", x="Patientaddmitedtointensivecareunit1yes0no", ci=False
)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(data=data, y="Platelets", x="Patientaddmitedtoregularward1yes0no", ci=False)
plt.xticks(rotation=90)
plt.show()

plt.figure(figsize=(6, 6))
sns.barplot(
    data=data, y="Platelets", x="Patientaddmitedtosemiintensiveunit1yes0no", ci=False
)
plt.xticks(rotation=90)
plt.show()